breedsim-mcp

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/musharna-breedsim-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

3 read · 0 write · 1 delete · 1 not yet classified

Secrets

None asked for

Install scripts

None found

Runs as

Python package

Tools (5)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• compare_programsCompare two programmes (paired, returns the difference)

  Compare two programmes on shared founders using paired seeds. final_only=true returns only the last cycle (`difference_is` and `favours` are always about the last cycle). Floats are rounded to 4 significant figures. Set a_selection_method/b_selection_method to contrast genomic against phenotypic selection — THE way to ask "is genotyping worth it on these founders". That contrast needs the pairing more than most, because the gap between the two methods is often smaller than seed-to-seed noise (sd 0.247 in one five-seed measurement), which two independent runs cannot see past. Read `differenc…

• describe_sessionDescribe a session

  Founder provenance, trait architecture, cycles run, reproducibility.

• found_populationCreate a founder population

  Found a population and its trait architecture, and keep it for later runs. generator="quickHaplo" is reproducible; "runMacs" is not, and says so in `reproducible` and `reason`. species only affects "runMacs", which has demographic histories for GENERIC, CATTLE, WHEAT and MAIZE — animal breeding as well as plant. n_snp_per_chr > 0 adds a SNP chip, which genomic selection needs and which can only be added here, at founding. The response then carries `linkage_disequilibrium`: READ IT BEFORE RUNNING GENOMIC SELECTION. If `has_linkage_disequilibrium` is false the markers are uninformative and an…

• list_methodsList engine capabilities and determinism status

  Engine versions, available founder generators, replicate floor, and whether THIS process is currently able to produce reproducible results.

• run_programRun a selection programme (returns distributions)

  Run the programme `replicates` times; return per-cycle mean, sd and 95% CI. final_only=true returns only the last cycle, for a question about where the programme ends; the warnings still read every cycle. To compare two programmes, call compare_programs, not run_program twice. Read `warnings`: `replicates_too_few` means the interval is too wide for the comparison, `variance_exhausted` that a still-rising mean is a plateau. Floats are rounded to 4 significant figures. There is no way to request a single run. In one five-seed measurement the spread was sd 0.247 on genetic gain, so one replicat…

Signals

Stars

0

Forks

0

Open issues

3

Weekly downloads

337

Last commit

Oct 23, 2026 (7 days ago)

Last release

Oct 20, 2026 (10 days ago)

Last package publish

Oct 20, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.musharna/breedsim-mcp

Version

0.6.1

Auth

No auth

Packages

pypi breedsim-mcp

License

GPL-3.0

Repository

github.com/musharna/breedsim-mcp

Website

github.com/musharna/breedsim-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql